93 citations · 279 across the 46 of their papers we have counts for
9 papers · 1 filter
Data Pruning via Moving-one-Sample-out
Haoru Tan, Sitong Wu, Fei Du +4
In this paper, we propose a novel data-pruning approach called moving-one-sample-out (MoSo), which aims to identify and remove the least informative samples from the training set.…
Denoising Diffusion Step-aware Models
Shuai Yang, Yukang Chen, Luozhou Wang +2
Denoising Diffusion Probabilistic Models (DDPMs) have garnered popularity for data generation across various domains. However, a significant bottleneck is the necessity for whole-n…
Mask-Attention-Free Transformer for 3D Instance Segmentation
Xin Lai, Yuhui Yuan, Ruihang Chu +3
Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial insta…
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
Yukang Chen, Shengju Qian, Haotian Tang +4
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, trainin…
FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
Yilun Chen, Zhiding Yu, Yukang Chen +4
False negatives (FN) in 3D object detection, {\em e.g.}, missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomou…
LISA: Reasoning Segmentation via Large Language Model
Xin Lai, Zhuotao Tian, Yukang Chen +4
Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target object…
Spherical Transformer for LiDAR-based 3D Recognition
Xin Lai, Yukang Chen, Fanbin Lu +2
LiDAR-based 3D point cloud recognition has benefited various applications. Without specially considering the LiDAR point distribution, most current methods suffer from information…
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
Yukang Chen, Jianhui Liu, Xiangyu Zhang +2
3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified…
IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation
Jianhui Liu, Yukang Chen, Xiaoqing Ye +1
Category-level 6D pose estimation aims to predict the poses and sizes of unseen objects from a specific category. Thanks to prior deformation, which explicitly adapts a category-sp…